• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.7
• /
• pp.2304-2320
• /
• 2021

Intelligently detecting anomalies in health sensor data streams (e.g., Electrocardiogram, ECG) can improve the development of E-health industry. The physiological signals of patients are collected through sensors. Timely diagnosis and treatment save medical resources, promote physical health, and reduce complications. However, it is difficult to automatically classify the ECG data, as the features of ECGs are difficult to extract. And the volume of labeled ECG data is limited, which affects the classification performance. In this paper, we propose a Generative Adversarial Network (GAN)-based deep learning framework (called CAB) for heart arrhythmia classification. CAB focuses on improving the detection accuracy based on a small number of labeled samples. It is trained based on the class-imbalance ECG data. Augmenting ECG data by a GAN model eliminates the impact of data scarcity. After data augmentation, CAB classifies the ECG data by using a Bidirectional Long Short Term Memory Recurrent Neural Network (Bi-LSTM). Experiment results show a better performance of CAB compared with state-of-the-art methods. The overall classification accuracy of CAB is 99.71%. The F1-scores of classifying Normal beats (N), Supraventricular ectopic beats (S), Ventricular ectopic beats (V), Fusion beats (F) and Unclassifiable beats (Q) heartbeats are 99.86%, 97.66%, 99.05%, 98.57% and 99.88%, respectively. Unclassifiable beats (Q) heartbeats are 99.86%, 97.66%, 99.05%, 98.57% and 99.88%, respectively.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1653-1661
• /
• 2022

In this study, the classification of cold water and normal water based on Geo-Kompsat 2A images was performed. Daily mean surface temperature products provided by the National Meteorological Satellite Center (NMSC) were used, and convolution neural network (CNN) deep learning technique was applied as a classification algorithm. From 2019 to 2022, the cold water occurrence data provided by the National Institute of Fisheries Science (NIFS) were used as the cold water class. As a result of learning, the probability of detection was 82.5% and the false alarm ratio was 54.4%. Through misclassification analysis, it was confirmed that cloud area should be considered and accurate learning data should be considered in the future.

• The korean journal of orthodontics
• /
• v.53 no.6
• /
• pp.358-364
• /
• 2023

Objective: This study aimed to three-dimensionally evaluate the pharyngeal airway space (PAS) of patients with anterior open bite (AOB) by using cone-beam computed tomography (CBCT) and compare the findings with those obtained in individuals with normal occlusion. Methods: The open bite group (OBG, n = 25) consisted of patients with an anterior overbite of -3 mm or less, while the control group (n = 25) consisted of age- and sex-matched individuals with an anterior overbite of 1-3 mm, Angle Class I malocclusion (1° ≤ point A-nasion-point B angle ≤ 4°), and a normodivergent profile (22° ≤ Frankfort mandibular plane angle ≤ 28°). After the CBCT data were reconstructed into a three-dimensional image, the PAS was segmented into four parts, and the volume of each part was measured. Pharyngeal airway length (PAL) and the area and transverse width of the part showing minimal constriction were also measured. Pearson's correlation analysis was used to evaluate the correlation between changes in the PAS and the amount of anterior overbite. Results: The OBG showed a significantly narrower airway space in the nasopharyngeal, hypopharyngeal, and total airway volumes. The OBG also showed a significantly smaller area and transverse width of the part with minimal constriction. The OBG showed a significantly longer PAL, but there was no correlation between the amount of anterior overbite and the changes in PAS. Conclusions: The PAS was associated with AOB. Patients with AOB had a narrower PAS and a smaller part showing minimal constriction.

• Animal Bioscience
• /
• v.37 no.1
• /
• pp.50-60
• /
• 2024

Objective: Testicular fat deposition has been reported to affect animal reproduction. However, the underlying mechanism remains poorly understood. The present study explored whether sperm meiosis and testosterone synthesis contribute to mouse testicular fat deposition-induced reproductive performance. Methods: High fat diet (HFD)-induced obesity CD1 mice (DIO) were used as a testicular fat deposition model. The serum hormone test was performed by agent kit. The quality of sperm was assessed using a Sperm Class Analyzer. Testicular tissue morphology was analyzed by histochemical methods. The expression of spermatocyte marker molecules was monitored by an immuno-fluorescence microscope during meiosis. Analysis of the synthesis of testosterone was performed by real-time polymerase chain reaction and reagent kit. Results: It was found that there was a significant increase in body weight among DIO mice, however, the food intake showed no difference compared to control mice fed a normal diet (CTR). The number of offspring in DIO mice decreased, but there was no significant difference from the CTR group. The levels of follicle-stimulating hormone were lower in DIO mice and their luteinizing hormone levels were similar. The results showed a remarkable decrease in sperm density and motility among DIO mice. We also found that fat accumulation affected the meiosis process, mainly reflected in the cross-exchange of homologous chromosomes. In addition, overweight increased fat deposition in the testis and reduced the expression of testosterone synthesis-related enzymes, thereby affecting the synthesis and secretion of testosterone by testicular Leydig cells. Conclusion: Fat accumulation in the testes causes testicular cell dysfunction, which affects testosterone hormone synthesis and ultimately affects sperm formation.

• Journal of Fisheries and Marine Sciences Education
• /
• v.25 no.4
• /
• pp.898-914
• /
• 2013

The fusion type human resources, it is a new human resources to scientific and technical information society of the future demands, and means to enjoy life with a creativity and expertise of fusion of various fields, to communicate in consideration of others. Fusion human resource education(STEAM), of "human resources to practice respect and compassion", "human resources equipped with communication skills", "human resources to pursue creativity and innovation" "human resources to understand the knowledge of the fusion to take advantage" in training I have presented to the area of core competence of the 4C 'Creativity"," Communication","Convergence', 'Caring'. In this study, the area of c ore competency for each element by elementary, middle, and high schools around the analysis of the target can be made by each school level to develop a practical program in the sense of basic research is to conduct. The findings are as follows: First, Area of Creativity, communication area, the contents fusion region, as well as care areas, to the detailed item capacity, the design of the class that contains the entire area should be performed. Second, Elementary and secondary school level analysis, design of the class containing the entire region up to capacity detail is required. High school was required study of school full of normal. Third, In general, for STEAM class environment and teaching model was developed by applying operations. Research and methods of teaching a wider variety of form was required. Later in this study is to develop programs and organize. and It intends to become the base to be able to interest and interest in science education by structured around the status of problems that can be found in the life of around themes STEAM.

• Journal of Science Education
• /
• v.38 no.1
• /
• pp.15-28
• /
• 2014

The purpose of this study was to analyze and compare the professionalism of elementary teachers in charge of teaching the science-gifted children, based on their personal variables, such as gender, educational career in normal class and gifted class, training in gifted education, academic degree, etc. For this study, the questionnaire was modified by referring to Choi's survey, and conducted to 98 teachers. The results of this study were as follows: In gender, the average of male teachers was significantly higher than the average of female teachers in their professionalism in gifted education. Regional difference was found in the teacher's professionalism, however, showed different aspects in the sub-domain. The teachers' professionalism in accordance with the career in education was no difference. In gifted education career, professionalism increased as high career in gifted education, especially, more than three years. As better educated, teachers' professionalism in responsibility and philosophical understanding for gifted education was increased significantly. The teachers' professionalism according to the degree of training related to gifted education was no significant difference. Overall, 'responsibility and philosophical understanding' and 'humanities-oriented quality' for gifted education were not greatly affected by teacher's personal variables in this study. Based on conclusions, implications for improving their professionalism in gifted education were discussed.

• The korean journal of orthodontics
• /
• v.52 no.1
• /
• pp.3-19
• /
• 2022

Objective: The purpose of this study was to investigate the accuracy of one-step automated orthodontic diagnosis of skeletodental discrepancies using a convolutional neural network (CNN) and lateral cephalogram images with different qualities from nationwide multi-hospitals. Methods: Among 2,174 lateral cephalograms, 1,993 cephalograms from two hospitals were used for training and internal test sets and 181 cephalograms from eight other hospitals were used for an external test set. They were divided into three classification groups according to anteroposterior skeletal discrepancies (Class I, II, and III), vertical skeletal discrepancies (normodivergent, hypodivergent, and hyperdivergent patterns), and vertical dental discrepancies (normal overbite, deep bite, and open bite) as a gold standard. Pre-trained DenseNet-169 was used as a CNN classifier model. Diagnostic performance was evaluated by receiver operating characteristic (ROC) analysis, t-stochastic neighbor embedding (t-SNE), and gradient-weighted class activation mapping (Grad-CAM). Results: In the ROC analysis, the mean area under the curve and the mean accuracy of all classifications were high with both internal and external test sets (all, > 0.89 and > 0.80). In the t-SNE analysis, our model succeeded in creating good separation between three classification groups. Grad-CAM figures showed differences in the location and size of the focus areas between three classification groups in each diagnosis. Conclusions: Since the accuracy of our model was validated with both internal and external test sets, it shows the possible usefulness of a one-step automated orthodontic diagnosis tool using a CNN model. However, it still needs technical improvement in terms of classifying vertical dental discrepancies.

• Horticultural Science & Technology
• /
• v.34 no.3
• /
• pp.495-509
• /
• 2016

Irrigation applications (IA) and increased bud load (BL) are fundamental practices that are used to achieve optimum yields in grape production, while maintaining fruit quality parameters. Two different irrigation amounts (IA-I and IA-II) based on growth stages, in addition to a non-irrigated (rain-fed) control, along with two different BL applications [normal bud load based on traditional pruning practices (1BL) and double bud load (2BL)] were evaluated over a two-year experiment for their effects on the biochemical composition of the berries. Berries from the rain-fed vines had higher sugar levels, whereas no significant change was detected in organic acid levels. The increased bud load (2BL) treatment yielded less sugar in the berries compared to the 1BL control in both years. The total non-colored phenolic compounds (NPC) were greater in the irrigated (especially IA-I) and 2BL treatments than in those of the rain-fed and 1BL control. However, total anthocyanin was greater in the non-irrigated and 1BL control than in the irrigated and 2BL treatments. The antioxidant contents of the berries also varied according to the treatments and years. Our results implied that implementing a higher bud load along with the IA-I irrigation application, in which irrigation applications were 50 and 75% of the cumulative evaporation from the Class A pan during berry set to veraison and veraison to harvest growth stages, respectively, can help in obtaining greater yields in high-plateau viticulture. Thus, if more buds are left on the vines, along with sufficient irrigation and rainfall, yield may increase while maintaining or increasing the biochemical composition of the berries.

• Journal of Climate Change Research
• /
• v.1 no.2
• /
• pp.121-131
• /
• 2010

This study was carried out to evaluate spatial variations in rice production areas by simulating rice growth and yield with CERES-Rice growth model under GCM $2{\times}CO_2$ climate change scenarios. A modified window version(v4.0) of CERES-Rice was used to simulate the growth and development of three varieties, representing early, medium, and late maturity classes. Simulated growth and yield data of the three cultivars under the climate for 1971 to 2000 was set as a reference. Compared with the current normal(1971 to 2000), heading period from transplanting to heading date decreased by 7~8 days for the climate in $2^{\circ}C$ increase over normal, and 16~18 days for the climate in UKMO with all maturity classes, while change of ripening period from heading to harvesting date was different with maturity classes. That is, physical maturity was shortened by 1~3 days for early maturity class and 14~18 days for late maturity class under different climate change scenarios. Rice yield was in general reduced by 4.5%, 8.2%, 9.9%, and 14.9% under the climate in $2^{\circ}C$, $3^{\circ}C$, $4^{\circ}C$, and about $5^{\circ}C$ increase, respectively. The yield reduction was due to increased high temperature-induced spikelet sterility and decreased growth period. The results show that predicted climate changes are expected to bring negative effects in rice production in Korea. So, it is required for introduction of new agricultural technologies to adapt to climate change, which are, for example, developing new cultivars, alternations of planting dates and management practices, and introducing irrigation systems, etc.

• Molecules and Cells
• /
• v.26 no.6
• /
• pp.536-547
• /
• 2008

Anthocyanidin synthase (ANS, leucoanthocyanidin oxygenase), a 2-oxoglutarate iron-dependent oxygenase, catalyzed the penultimate step in the biosynthesis of the anthocyanin class of flavonoids, from the colorless leucoanthocyanidins to the colored anthocyanidins. The full-length cDNA and genomic DNA sequences of ANS gene (designated as GbANS) were isolated from Ginkgo biloba for the first time. The full-length cDNA of GbANS contained a 1062-bp open reading frame (ORF) encoding a 354-amino-acid protein. The genomic DNA analysis showed that GbANS gene had three exons and two introns. The deduced GbANS protein showed high identities to other plant ANSs. The conserved amino acids (H-X-D) ligating ferrous iron and residues (R-X-S) participating in 2-oxoglutarate binding were found in GbANS at the similar positions like other ANSs. Southern blot analysis indicated that GbANS belonged to a multi-gene family. The expression analysis by real-time PCR showed that GbANS expressed in a tissue-specific manner in G. biloba. GbANS was also found to be up-regulated by all of the six tested abiotic stresses, UV-B, abscisic acid, sucrose, salicylic acid, cold and ethylene, consistent with the promoter region analysis of GbANS. The recombinant protein was successfully expressed in E. coli strain with pET-28a vector. The in vitro enzyme activity assay by HPLC indicated that recombinant GbANS protein could catalyze the formation the cyanidin from leucocyanidin and conversion of dihydroquercetin to quercetin, suggesting GbANS is a bifunctional enzyme within the anthocyanidin and flavonol biosynthetic pathway.